Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to strong or impactful actions and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    word stems followed by suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.75
    ---*/
    -0.56
    ||}
    -0.55
    ########.
    -0.54
     buta
    -0.52
     basta
    -0.51
     dali
    -0.51
    })$}
    -0.51
     تكبرها
    -0.50
     imam
    -0.50
    POSITIVE LOGITS
     leiding
    0.68
     boneca
    0.66
     tæ
    0.65
     beschik
    0.65
     avoient
    0.63
     betrek
    0.62
    addCriterion
    0.61
     auroit
    0.61
     soggior
    0.60
     verantwoorde
    0.60
    Act Density 0.034%

    No Known Activations